Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2058 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.7001. Min Act: -0.1700

Data Index: 5160097 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.6501. Min Act: -0.1700

Data Index: 7010065 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.6265. Min Act: -0.1700

Data Index: 4602663 (Open Web Text)

Max Activating Token Index: 35

Text #3

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5879. Min Act: -0.1700

Data Index: 3236222 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5658. Min Act: -0.1700

Data Index: 7845239 (Open Web Text)

Max Activating Token Index: 750

Text #5

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5294. Min Act: -0.1700

Data Index: 5890404 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5530. Min Act: -0.1700

Data Index: 6359139 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5683. Min Act: -0.1700

Data Index: 2760028 (Open Web Text)

Max Activating Token Index: 83

Text #8

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5454. Min Act: -0.1700

Data Index: 5853725 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5149. Min Act: -0.1700

Data Index: 3459479 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5211. Min Act: -0.1700

Data Index: 5438785 (Open Web Text)

Max Activating Token Index: 673

Text #11

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5209. Min Act: -0.1700

Data Index: 4111142 (Open Web Text)

Max Activating Token Index: 560

Text #12

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5255. Min Act: -0.1700

Data Index: 5393821 (Open Web Text)

Max Activating Token Index: 606

Text #13

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5358. Min Act: -0.1700

Data Index: 4410054 (Open Web Text)

Max Activating Token Index: 605

Text #14

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5183. Min Act: -0.1700

Data Index: 3430161 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5341. Min Act: -0.1700

Data Index: 8323375 (Open Web Text)

Max Activating Token Index: 31

Text #16

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5394. Min Act: -0.1700

Data Index: 3250602 (Open Web Text)

Max Activating Token Index: 314

Text #17

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5490. Min Act: -0.1700

Data Index: 5190664 (Open Web Text)

Max Activating Token Index: 662

Text #18

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.4776. Min Act: -0.1700

Data Index: 1048799 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 3.7001. Min Range: -3.7001

Max Act: 3.5047. Min Act: -0.1700

Data Index: 2884724 (Open Web Text)

Max Activating Token Index: 54